MCP Agent Platform
A modular platform that enables LLM agents to discover, register, and execute both local tools and tools from external MCP servers, with REST APIs for server management and Streamable HTTP support.
README
MCP Agent Platform
A modular Model Context Protocol (MCP) agent platform built with Python.
This project allows an LLM-powered agent to work with both local tools and tools exposed by external MCP servers. It provides MCP server management, dynamic tool discovery, tool registration, tool execution, and multi-step tool calling.
🚀 Project Overview
The MCP Agent Platform acts as a bridge between an LLM and multiple tools.
The agent can:
- Register local Python tools
- Connect to external MCP servers
- Discover tools dynamically from MCP servers
- Convert MCP tools into OpenAI-compatible function schemas
- Allow the LLM to decide which tool to use
- Execute the selected tool
- Send tool results back into the LLM context
- Execute multiple tools sequentially when required
- Return the final natural-language response
- Manage MCP server connections through REST APIs
- Expose an MCP server over Streamable HTTP
🏗️ Architecture
┌──────────────────────┐
│ User │
└──────────┬───────────┘
│
▼
┌──────────────────────┐
│ Agent / LLM │
│ OpenAI API │
└──────────┬───────────┘
│
Tool selection
│
▼
┌──────────────────────┐
│ Tool Registry │
└──────────┬───────────┘
│
┌─────────────────┴─────────────────┐
│ │
▼ ▼
┌───────────────────┐ ┌───────────────────┐
│ Local Tools │ │ MCP Tools │
│ │ │ │
│ get_weather │ │ External MCP │
│ get_datetime │ │ Servers │
└─────────┬─────────┘ └─────────┬─────────┘
│ │
│ ▼
│ ┌──────────────────┐
│ │ MCP Manager │
│ └────────┬─────────┘
│ │
│ ▼
│ ┌──────────────────┐
│ │ MCP Server(s) │
│ │ Streamable HTTP │
│ └────────┬─────────┘
│ │
└──────────────────┬───────────────┘
│
▼
Tool Result
│
▼
LLM
│
▼
Final ResponseRecommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.